diff_bee

[diff_bee @richajoy]

AI meets faith. No more waiting for answers. Ask private, judgment-free questions about God and life’s toughest topics—anytime. That’s FaithPal. 🙏🤖

[mark @markletree]

At @coinbase our AI spend is down nearly half this quarter while token usage keeps climbing. My team built the infrastructure behind it: routing, caching, cheaper defaults, and the spend services that track it.

We route everything through our own gateway: a single endpoint and format for dozens of models, with cross-provider failover, redaction, logging, and cost controls all applied before anything reaches a vendor.

We started with cheaper defaults and caching. 91% of employees weren't hitting their usage caps. Instead of lowering caps, we set cheaper model defaults to cut spend. Caching took more work to get consistent across every tool and model family. A cache hit needs the prefix to match exactly, so we keep building a long, stable prefix across turns. Each request only pays full rate on the new tokens and reads the rest from cache.

Our routing accounts for caching too. The naive approach scores each turn on its own and sends it to whichever model fits, which seems reasonable but would run up spend. The cache is per-model, so switching mid-conversation invalidates it. Our router weighs cache state alongside how hard the task is: a conversation keeps its model while the cache is warm, and the chance to re-route comes only when it goes quiet long enough for the TTL to lapse. Once it does, the router is free again to pick the best model for the task.

These improvements happened at the gateway, so they apply across every team and tool. Next we're going deeper on the coding harness, where we have the most signal and flexibility, tuning how subagents and context get managed.

[diff_bee @richajoy]

@deedydas @steipete Love to join future sessions!

[Philip Kiely @philipkiely]

https://t.co/LlNSUlxWLa

[Raúl Conte @raulcontev]

Mi compañero de trabajo tiene 45 años y ha pasado por:

2 matrimonios
Ha perdido a sus padres
Problemas serios de salud
Bancarrota

Le pregunté qué lo hace seguir adelante,

su respuesta me hizo olvidar mis propios problemas:

[Ivanka Trump @IvankaTrump]

Loved this video mashup.

Good luck to all the entrepreneurs doing the hard, meaningful work of building!

1. Value is everything
Build something people genuinely want, not something clever.
A business only works if it creates value and can capture it.

2. Solve real, painful problems
The strongest companies remove friction, save time, or eliminate frustration.
If it feels optional, it likely is.

3. Distribution matters as much as product
A great product without reach is invisible.
Winning companies obsess over how they get in front of people.

4. Focus is a competitive advantage
Most people dilute their energy.
Great founders concentrate on a few high-leverage moves and ignore the rest.

5. Speed compounds
Iteration beats perfection.
Launch, learn, refine, repeat, faster than feels comfortable.

6. Simplicity scales
The best businesses are easy to understand, easy to use, and easy to explain.
Complexity is friction disguised as sophistication.

7. Mindset is not soft, it is structural
Resilience, long-term thinking, and tolerance for discomfort are not personality traits, they are requirements.

8. Build for longevity, not noise
Short-term hacks create spikes.
Enduring companies are built on trust, brand, and consistency.

9. Leverage is the force multiplier that transforms effort into scale.
Technology, media, capital, and people multiply output.
The goal is not to work harder, but to work in systems that scale.

10. Execution is the separator
Ideas are abundant.
Relentless, disciplined execution is rare.

The essence : find a meaningful problem, solve it simply, distribute it aggressively, and execute with focus over the long term.

[diff_bee @richajoy]

@MainzOnX Yes pls

[diff_bee @richajoy]

@EvanLuthra @grok brief the video

[diff_bee @richajoy]

@grok @grok does grok api support Indian language Malayalam

[diff_bee @richajoy]

@GoogleLabs @grok how’s it going to help and what’s the product features

[diff_bee @richajoy]

https://t.co/3p1zUnxw9t

[diff_bee @richajoy]

@chddaniel @claudeai Ship

[Reads with Ravi @readswithravi]

This video by Scott Adams will rewire your brain to never feel lazy again. Excellent insight.

[diff_bee @richajoy]

@trq212 @burkov I felt this several months back!

[Rohan Paul @rohanpaul_ai]

Good GPU performance summaries - in 6 mints.

[diff_bee @richajoy]

@paulg Not allowing to do federal agents its duty will have repercussions!

[diff_bee @richajoy]

@AlexFinn Why shift+enter doesn’t work?

[diff_bee @richajoy]

@bentossell Can we have an audible option for these articles? @nikitabier @elonmusk

[Sahil Bloom @SahilBloom]

https://t.co/b6dxLaCqAn

[Adam @adamdotdev]

Man how lucky are millennial devs, just as we’re getting too old and tired for this job, all the tedium gets magically removed and there’s an amplifier that makes all of our knowledge 1000x more useful (and necessary)

[hari raghavan @haridigresses]

Corollary: this is the best possible time for semi-technical non-engineers to catch up.

Over the last 3 months, I went from someone who was a "technical PM" to ridiculously proliferous at shipping massive amounts of (what appears to be) quality code.

Systems thinking + domain expertise are now FAR more important than the syntax of individual lines of code. In fact... getting caught up in the lines of code might actually be a hinderance.

For context: I learned C++ in high school, then I was an Excel-monkey in my consulting days (but building complex models over 10-20 weeks that were basically data applications). I forgot any form of syntax over the last 20 years but the other experiences meant I built strong foundations in object-oriented programming, proper abstractions, systems thinking, and data structures. And I've spent most of my career in Finance, Biz Ops, Legal, HR... which means that I can be monstrously productive in building software for corporate finance teams.

How productive?

500k+ LoC touched and hundreds of commits, in 11 weeks. Yes, yes, I know lines of code is not a KPI to optimize, but someone going from 0 to that order of magnitude should still paint a picture.

And this isn't slop. It's reviewed by actual engineers on the team, and we're rigorous about PR reviews (in the earlier days I had to redo PRs from scratch many, many times because it wasn't good enough).

The overall process works beautifully, because I have the multi-year product roadmap and the codebase architecture in my head. I'm able to consider future needs, and execute on a months-long roadmaps... in days.

I genuinely feel like I just got access to a video game I've been yearning to play, for a long time... and somehow my copy came with God mode baked in.

(This is funny because Andrej Karpathy is actually a god in this space and I'm probably just getting used to the power of building software, and just a teeny bit of Dunning-Kruger to boot...)

But still. I share this because I chatted a few days ago with a close friend who's a really sharp systems thinker but not an engineer, who said "I feel like I missed the wave, it's too late for me to pick up vibecoding."

I told him that I only began working in our codebase in earnest in early October. That things are changing so fast that those who previously learned to code are having to sprint really hard to keep up, too. That knowing the line-by-line syntax isn't the most critical for *most* products. That the game is changing every week... but that's a huge gift people like us, because it gives us a place to stand in order to move the world.

And most of all, that if you're a systems thinker, have good taste in UI/UX, have domain expertise, and — I think this is somewhat important — that you love software... there is absolutely nothing stopping you from building something amazing.

I *love* software. I thought several times about taking a detour to learn how to code, but life just never slowed down enough. Ironically, it was the practice of coding speeding up that gave me the opportunity to get on board.

However long this lasts, I feel so fortunate to be able to actually get in there, and build something that I love.